{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T17:40:42Z","timestamp":1779385242397,"version":"3.53.1"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100015599","name":"Toyota Research Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015599","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,9,27]]},"DOI":"10.1109\/iros51168.2021.9636023","type":"proceedings-article","created":{"date-parts":[[2021,12,16]],"date-time":"2021-12-16T20:45:38Z","timestamp":1639687538000},"page":"8913-8920","source":"Crossref","is-referenced-by-count":19,"title":["Generalization Through Hand-Eye Coordination: An Action Space for Learning Spatially-Invariant Visuomotor Control"],"prefix":"10.1109","author":[{"given":"Chen","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ajay","family":"Mandlekar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Fei-Fei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Silvio","family":"Savarese","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Danfei","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.2988642"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196733"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3004787"},{"key":"ref32","article-title":"Learning to compose hierarchical object-centric controllers for robotic manipulation","author":"sharma","year":"2020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(99)01327-3"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/279943.279964"},{"key":"ref37","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.035"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3377930.3389847"},{"key":"ref10","article-title":"Learning interactively to resolve ambiguity in reference frame selection","author":"franzese","year":"0"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593986"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2002.1014739"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.21-17-06917.2001"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JRA.1987.1087068"},{"key":"ref14","first-page":"10724","article-title":"Unsupervised learning of object keypoints for perception and control","author":"kulkarni","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989046"},{"key":"ref16","author":"levine","year":"2016","journal-title":"End-to-end training of deep visuomotor policies"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-36802-9_25"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968114"},{"key":"ref19","article-title":"Learning to generalize across longhorizon tasks from human demonstrations","author":"mandlekar","year":"2020"},{"key":"ref28","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"ross","year":"2010","journal-title":"AISTATS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2010.936947"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s00221-009-1781-x"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487173"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1167\/7.14.16"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917743795"},{"key":"ref8","article-title":"Dense object nets: Learning dense visual object descriptors by and for robotic manipulation","author":"florence","year":"2018","journal-title":"Conference on Robot Learning"},{"key":"ref7","article-title":"One-shot visual imitation learning via meta-learning","author":"finn","year":"2017","journal-title":"Conference on Robot Learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30301-5_60"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2956365"},{"key":"ref1","first-page":"103","article-title":"A framework for behavioural cloning","volume":"15","author":"bain","year":"1995","journal-title":"Machine Intelligence"},{"key":"ref20","article-title":"Roboturk: A crowdsourcing platform for robotic skill learning through imitation","author":"mandlekar","year":"2018"},{"key":"ref22","article-title":"Keypoints into the future: Self-supervised correspondence in model-based reinforcement learning","author":"manuelli","year":"2020"},{"key":"ref21","author":"manuelli","year":"2019","journal-title":"kpam Keypoint affordances for category-level robotic manipulation"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461249"},{"key":"ref24","first-page":"12350","article-title":"Towards interpretable reinforcement learning using attention augmented agents","author":"mott","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref41","article-title":"Visual attention guided deep imitation learning","author":"zhang","year":"0"},{"key":"ref23","first-page":"2204","article-title":"Recurrent models of visual attention","author":"mnih","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref44","article-title":"Robosuite: A modular simulation framework and benchmark for robot learning","author":"zhu","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196971"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461249"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2009.5353894"}],"event":{"name":"2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Prague, Czech Republic","start":{"date-parts":[[2021,9,27]]},"end":{"date-parts":[[2021,10,1]]}},"container-title":["2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9635848\/9635849\/09636023.pdf?arnumber=9636023","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:54:45Z","timestamp":1652201685000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9636023\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,27]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/iros51168.2021.9636023","relation":{},"subject":[],"published":{"date-parts":[[2021,9,27]]}}}